ppo-Huggy / run_logs /timers.json
Alrcatraz's picture
Huggy
df51774 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046965837478638,
"min": 1.4046919345855713,
"max": 1.4301029443740845,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69924.390625,
"min": 67695.3671875,
"max": 78774.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.72583479789104,
"min": 84.23037542662117,
"max": 389.3720930232558,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49916.0,
"min": 49054.0,
"max": 50229.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999743.0,
"min": 49608.0,
"max": 1999743.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999743.0,
"min": 49608.0,
"max": 1999743.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.39605712890625,
"min": 0.07589375972747803,
"max": 2.4937620162963867,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1363.3565673828125,
"min": 9.714401245117188,
"max": 1461.3446044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6706993240463714,
"min": 1.83879670931492,
"max": 3.95352423292286,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2088.6279153823853,
"min": 235.36597879230976,
"max": 2293.3920118808746,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6706993240463714,
"min": 1.83879670931492,
"max": 3.95352423292286,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2088.6279153823853,
"min": 235.36597879230976,
"max": 2293.3920118808746,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014909037513684276,
"min": 0.01336667937769865,
"max": 0.02070314012768601,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04472711254105283,
"min": 0.0267333587553973,
"max": 0.060030396702738166,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057331918345557314,
"min": 0.021150887540231148,
"max": 0.06285629442168607,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17199575503667194,
"min": 0.042301775080462296,
"max": 0.18856888326505822,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3464988845333273e-06,
"min": 3.3464988845333273e-06,
"max": 0.000295258726580425,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0039496653599982e-05,
"min": 1.0039496653599982e-05,
"max": 0.0008436649687783498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111546666666664,
"min": 0.10111546666666664,
"max": 0.19841957500000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033463999999999,
"min": 0.20737164999999996,
"max": 0.58122165,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.566178666666658e-05,
"min": 6.566178666666658e-05,
"max": 0.0049211367925,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019698535999999973,
"min": 0.00019698535999999973,
"max": 0.014062960334999998,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1739546493",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739549085"
},
"total": 2591.817227443,
"count": 1,
"self": 0.44019076999984463,
"children": {
"run_training.setup": {
"total": 0.024584484000001794,
"count": 1,
"self": 0.024584484000001794
},
"TrainerController.start_learning": {
"total": 2591.352452189,
"count": 1,
"self": 4.717564876045799,
"children": {
"TrainerController._reset_env": {
"total": 3.0497330670000338,
"count": 1,
"self": 3.0497330670000338
},
"TrainerController.advance": {
"total": 2583.463699236954,
"count": 232205,
"self": 5.376424209912329,
"children": {
"env_step": {
"total": 2088.9483739780517,
"count": 232205,
"self": 1634.893839781953,
"children": {
"SubprocessEnvManager._take_step": {
"total": 451.13087324410014,
"count": 232205,
"self": 16.49609705611647,
"children": {
"TorchPolicy.evaluate": {
"total": 434.6347761879837,
"count": 222913,
"self": 434.6347761879837
}
}
},
"workers": {
"total": 2.923660951998613,
"count": 232205,
"self": 0.0,
"children": {
"worker_root": {
"total": 2583.5632489020754,
"count": 232205,
"is_parallel": true,
"self": 1256.2034533371962,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011440079999829322,
"count": 1,
"is_parallel": true,
"self": 0.00024242799997864495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009015800000042873,
"count": 2,
"is_parallel": true,
"self": 0.0009015800000042873
}
}
},
"UnityEnvironment.step": {
"total": 0.03156422800009295,
"count": 1,
"is_parallel": true,
"self": 0.0003285390001792621,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002030999999078631,
"count": 1,
"is_parallel": true,
"self": 0.0002030999999078631
},
"communicator.exchange": {
"total": 0.030250000000023647,
"count": 1,
"is_parallel": true,
"self": 0.030250000000023647
},
"steps_from_proto": {
"total": 0.0007825889999821811,
"count": 1,
"is_parallel": true,
"self": 0.00021859399998902518,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005639949999931559,
"count": 2,
"is_parallel": true,
"self": 0.0005639949999931559
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1327.3597955648793,
"count": 232204,
"is_parallel": true,
"self": 38.790659375782525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.08395642993742,
"count": 232204,
"is_parallel": true,
"self": 86.08395642993742
},
"communicator.exchange": {
"total": 1109.8099043140965,
"count": 232204,
"is_parallel": true,
"self": 1109.8099043140965
},
"steps_from_proto": {
"total": 92.67527544506277,
"count": 232204,
"is_parallel": true,
"self": 34.70156650604497,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.9737089390178,
"count": 464408,
"is_parallel": true,
"self": 57.9737089390178
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 489.13890104898996,
"count": 232205,
"self": 7.28316013893334,
"children": {
"process_trajectory": {
"total": 176.52206011605665,
"count": 232205,
"self": 174.90862472205663,
"children": {
"RLTrainer._checkpoint": {
"total": 1.613435394000021,
"count": 10,
"self": 1.613435394000021
}
}
},
"_update_policy": {
"total": 305.333680794,
"count": 97,
"self": 239.06119831198453,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.27248248201545,
"count": 2910,
"self": 66.27248248201545
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.139998837781604e-07,
"count": 1,
"self": 9.139998837781604e-07
},
"TrainerController._save_models": {
"total": 0.12145409499999005,
"count": 1,
"self": 0.00194617199986169,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11950792300012836,
"count": 1,
"self": 0.11950792300012836
}
}
}
}
}
}
}